FR2870378A1 - Person e.g. aged person, fall detecting method for use in e.g. home, involves providing exposing unit for successive exposures of same plane, and detecting reduction in height of outline form beyond chosen threshold interval - Google Patents

Person e.g. aged person, fall detecting method for use in e.g. home, involves providing exposing unit for successive exposures of same plane, and detecting reduction in height of outline form beyond chosen threshold interval Download PDF

Info

Publication number
FR2870378A1
FR2870378A1 FR0405356A FR0405356A FR2870378A1 FR 2870378 A1 FR2870378 A1 FR 2870378A1 FR 0405356 A FR0405356 A FR 0405356A FR 0405356 A FR0405356 A FR 0405356A FR 2870378 A1 FR2870378 A1 FR 2870378A1
Authority
FR
France
Prior art keywords
person
height
characterized
method according
detecting
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
FR0405356A
Other languages
French (fr)
Other versions
FR2870378B1 (en
Inventor
Arnaud Fourniquet
Pierre Wagner
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Electricite de France SA
Original Assignee
Electricite de France SA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Electricite de France SA filed Critical Electricite de France SA
Priority to FR0405356A priority Critical patent/FR2870378B1/en
Publication of FR2870378A1 publication Critical patent/FR2870378A1/en
Application granted granted Critical
Publication of FR2870378B1 publication Critical patent/FR2870378B1/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/04Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0407Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
    • G08B21/0415Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting absence of activity per se
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/04Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0407Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
    • G08B21/043Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
    • G08B21/02Alarms for ensuring the safety of persons
    • G08B21/04Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0438Sensor means for detecting
    • G08B21/0476Cameras to detect unsafe condition, e.g. video cameras

Abstract

The method involves providing an exposing unit e.g. camera, for successive exposures of a same plane. A movement is detected in the exposures, to identify a movement representing shape of a person (IND). An outline form (REC) of the movement representing shape is located. Reduction in height of the form (REC) beyond a chosen threshold interval is detected, where the reduction is representative of a fall of the person. Independent claims are also included for the following: (A) a computer program product stored in a memory of a processing unit or on a removable medium intended to cooperate with a reader of the processing unit, including instructions for implementing a method of detecting fall of a person (B) a device for detecting fall of a person in restricted autonomy.

Description

Method for detecting falls at home, in particular

  The invention relates to the detection of falls of persons with limited autonomy, typically elderly people maintained at home.

  Recently, the news has sadly shown that elderly people, prone to serious discomfort, such as heart attacks, were unattended at home, especially in the summer, which often resulted in the death of these people.

  Document FR-2828317 discloses an autonomous method for detecting abnormal situations incurred by an individual operating in a defined environment, in which several sensors connected to a central unit are arranged and comprising steps of: learning a mean activity , identification and characterization of an activity, comparison of the actual activity in progress with the average activity, and possibly intervention decision.

  However, such sensors are to be expected in large numbers and the technique of FR-2828317, although very promising, has proved heavy use and maintenance in individuals.

  The present invention improves the situation.

  To this end, it proposes a detection method comprising the following steps: a) providing a device for taking successive shots of the same plane, b) detecting in said shots a movement to identify a representative moving form of a person, particularly with limited autonomy, c) identify a contour of said moving form, and d) detect a decrease in height of said contour shape, beyond a chosen threshold difference, said decrease being representative of a fall of said person.

  Thus, according to one of the advantages afforded by the present invention, from a simple camera, such as a camera, preferentially connected to simple computer means such as a central computer unit, one reliably detects a fall of the person, with a low rate of false alarms, as will be seen hereinafter.

  Moreover, other characteristics and advantages of the invention will become apparent upon examination of the detailed description below, and the accompanying drawings, in which: FIG. 1 schematically represents a device for detecting falls of persons within the meaning of 2a, 2b and 2c schematically show shots of an IND indi- vidual evolving in its habitat at different respective times t1, t1 and t2; FIG. 3 schematically represents a preferred rectangular shape of the individual moving in his habitat; and Figure 4 illustrates a flow diagram of the detection steps in a preferred embodiment of the invention.

  Reference is first made to FIG. 1, in which a detection device has been shown in the sense of the present invention, preferably comprising: - shooting means comprising a CAM camera, preferably a wide angle camera, mechanically connected FIX fixing means for installing the CAM camera in a privileged location of the habitat of a person with limited autonomy, - and a CPU processing unit connected to the CAM camera.

  The CAM camera takes successive images preferentially in black and white and it is advantageously sensitive in the near infrared to operate at night. In addition, it will be possible to provide infrared illumination means for better visibility at night.

  The CPU processing unit comprises, as a conventional central unit of a computer, preferentially: an acquisition card CG connected to the CAM camera, for acquiring in digital form the image data taken successively by the camera; PROC processor adapted to cooperate with the GC acquisition card to estimate including a contour of a shape whose movement is located from one acquired image to another, under the control of a computer program.

  Advantageously, the PROC processor is equipped with an internal clock (not shown) in particular to carry out a delay during a contour shape modification detection and thus avoid triggering a false alarm.

  The device of the invention may furthermore include, but not necessarily, an ECR display monitor of the acquired images, generally connected to the acquisition card CG, as well as input means such as a keyboard CLA or a mouse ( not shown). This equipment may be provided for a preliminary phase of installation and adjustment / calibration of the detection device. However, after this phase they are no longer needed. For this purpose, they are represented in broken lines in FIG.

  The processing unit UC furthermore comprises a memory MEM in particular for storing a computer program product which includes instructions for the implementation of all or part of the steps of the method within the meaning of the invention and which will be described in detail. below. It is simply indicated here that the computer program can also be stored initially on a removable medium intended to cooperate with a reader LEC of the processing unit UC, in particular a CD-ROM reader, floppy disk or the like, or be downloaded from a server via a communication network (Internet in particular) to which can advantageously be connected a COM communication interface that includes the processing unit UC.

  It is furthermore indicated that, in an advantageous embodiment, the COM communication interface (typically a modem, a modem card, or the like) can trigger a telephone call with a dedicated voice message to a remote entity EXT, in case prolonged detection of an abnormal modification of the contour shape. This remote entity EXT can for example be a specialized organization such as a central standard of emergency medical service, or a fire station.

  It will be understood that the above computer program product is an important means for implementing the present invention. In this respect, the invention also aims at such a computer program product, as well as a detection device storing in a memory this computer program product.

  FIG. 2a shows an individual IND, typically a person with limited autonomy, who evolves in his habitat. More particularly, Figure 2a shows an image taken at an instant to, at a wide angle. In FIG. 2b, the same IND individual is shown which has moved with respect to the IM (to) image of FIG. 2a. More particularly, FIG. 2b represents the same shot, at the same angle and with the same focus, as the IM (to) image of FIG. 2a, but at a later time t1.

  Advantageously, the method within the meaning of the invention comprises a first calibration step to identify only one form of global outline for a person in motion. Alternatively, the method assigns a contour shape to each object spotted in motion in the successive images. In this embodiment, the presence of a pet is recognized, the dimensions of which are previously identified so that no follow-up of its movements is then carried out.

  More generally, this first calibration step consists first of all in identifying a moving form in the habitat setting of the individual IND. Typically, a graphic processing by computer means known per se can identify a moving form IND in a fixed setting between two instants to and t1.

  Thus, during this calibration step, the two IM (to) and IM (tl) images of the respective figures 2a and 2b are compared to record a local displacement of a shape in the images acquired, in this case the individual. IND.

  Referring to FIG. 2b and FIG. 3, the outline shape is, in a preferred embodiment, a REC rectangle of height a1 and width b1. A decrease in the height ai of the rectangle REC above a threshold difference, which will be described later, is preferably detected.

  Indeed, with reference to Figure 2c, it is understood that when the height of the rectangle REC is less than a chosen threshold, the individual IND is necessarily in a supine position on the floor. More particularly, FIG. 2c shows the individual IND in a recumbent, unusual position (in a room without a bed or with a height a of the rectangle REC less than a usual rectangle height when the individual IND is sitting on a chair or on an armchair of the decoration of figure 2c). Thus, between time t1 of FIG. 2b and time t2 of FIG. 2c, the height of the rectangle REC has shown a sharp decrease and beyond the selected threshold difference, mentioned above. This situation corresponds to a start of warning triggering. As will be seen below, if the immobility of the individual IND after the time t2 is noted, the alert is effective and an alarm is triggered from a specialized body monitoring persons with limited autonomy.

  However, it will be understood that it is more advantageous to define a ratio r between the height a1 and the width b1 of the rectangle REC (FIG. 3), insofar as the individual IND can move backward or forward relative to the CAM camera, during his movements, which, of course, modifies the absolute height al of the individual IND in the acquired image.

  Referring now to Figure 4 to describe the main steps of a method in the sense of the present invention, in a preferred embodiment.

  During a first step 41, an IM image is acquired. Repetitively, one acquires at successive moments new images, of the same scene of a habitat of an individual IND. In step 42, it is tested whether, in a newly acquired image, a particular shape, in motion, has been identified. If this is the case (arrow o from test 42), in step 43, a rectangle REC, of height a1 and of width b1 is identified. Once this moving form, identified by a preferentially rectangular contour REC, has been identified and identified as corresponding to the person with limited autonomy that it is desired to follow, it is carried out in step 44 a tracking (or "tracking") ) of the moving form, triggered at instant to. Preferably, in step 45, the ratio of the height of the rectangle to the width b1 (or simply the height a1 in a less sophisticated embodiment) is stored, in correspondence of the instant to. Of course, this ratio al / bl stored in memory as a reference report can change later, especially if the person monitored IND sits slowly, as will be seen below, or other.

  Thus, it will be understood that this tracking step consists in: cl) tracking an identified moving form (step 44), and c2) correcting, if necessary, changes in the shape contour as a function of this tracking ( step 52 described later).

  From instant to, it evaluates, at a given clock rate, the ratio of the height a1 of the moving rectangle over its width bi at successive current instants tc. More particularly, in step 46, it is tested whether the ratio stored at time to and noted r (to) is greater than the ratio measured at the current time t, and noted r (t,). Above all, if this difference r (to) -r (tc) is greater than a chosen threshold SR, a potential alarm situation is decreed. However, it is sought to evacuate the cases of false alarms, in the detection as defined herein. invention. Thus, in step 47, it is tested whether the difference between the current time tc and the initialization time to is less than a first predetermined threshold duration St1. For example, this duration St]. is of the order of 2 seconds.

  If this duration is greater than the threshold St1, this situation simply corresponds, for example, to a case where the individual IND has bent down to pick up an object, or, more generally, has leaned beyond the threshold SR, slowly, which corresponds to a normal movement for a person with limited autonomy, such as an elderly person.

  On the other hand, the significance of the arrow n exiting the test conducted in step 47 is justified as follows.

  It is considered here that, in the intended application, persons with limited autonomy are deemed to be slow movements. Thus, if for example more than 2 seconds have elapsed (the duration St].) Between the instant of detection of the current ratio al / bl, which is lower than the threshold SR (test of step 46), this can simply mean that the older person bows slowly to the ground, for example to pick up an object or something else. On the other hand, if the time difference tc-to is less than 2 seconds, it means that the reduction in the height of the rectangle corresponding to the shape of the outline of the elderly person is brutal, which means that the elderly person has fallen just as abruptly on the ground.

  It is also indicated that the decoration shown in FIGS. 2a to 2c can also be a bedroom, in which case the IND can lie on a bed. In this case, the effective alarm is triggered in step 51 only if the person goes to bed abruptly, in less than 2 seconds (the duration St1). This measure avoids the triggering of false alarms when an elderly person goes to bed slowly, without any particular risk to his health.

  Thus, it will be understood that the method, in this preferred embodiment, comprises the steps consisting in: d1) comparing the height al (or preferably the alibi ratio) of the contour shape REC with a first date to at height or the same alibi ratio) of the same contour shape at a second time tc, current (test step 47), and d2) decree a potential alert under the following conditions: * if the difference in heights is greater than the difference threshold SR, and * if the difference tc-to between the first and second dates is less than a first threshold duration St1, predetermined, and for example close to 2 seconds (step 50).

  In fact, in step 50, a time t1 of potential alarm Ali is stored in a memory of the detection device and the alibi ratio associated with the instant ti and noted r (t1) C 'is also memorized. is the test carried out in step 48 which is decisive for whether it is appropriate, in the present situation, to trigger an effective alarm in step 51. In fact, in step 48, it is run again. detection time and is particularly noted if it has elapsed since time ti (stored in step 50) a second threshold time St2, for example close to ten seconds. If this is the case, an alarm is triggered in step 51 from the communication interface COM of the detection device.

  Thus, the method in the sense of the invention then comprises a group of steps consisting in: e) counting a duration from the detection of the fall, and f) triggering an alarm for a duration exceeding a second predetermined threshold duration for example ten seconds.

  Thus, it will be understood that from the moment when a decrease in the alibi ratio to the test 46 was detected, on the one hand, and the alarm tripping moment in step 51, on the other hand, it was is elapsed a total duration less than or equal to St1 + St2, or substantially a dozen seconds. On the other hand, if the duration St2 has elapsed since time t1 (arrow n of test 48), it is detected whether the alibi ratio at the current instant tc is greater than the ratio r (t1) stored previously. in step 50. If this test of step 49 is negative, which means that there has been no change in the position of the individual IND since time t1i, we continue to increment temporally the value of the current time tc until reaching the second threshold duration St2 and triggering the alarm in step 51. On the other hand, if the test of step 49 is positive (arrow o), this situation finally corresponds to a case where the individual IND simply lowered quickly but rose normally afterwards. In this case, steps 46 and following are simply repeated, again fixing as an alibi report the initial reference ratio r (to) initial.

  Thus, the test of step 49 advantageously avoids false alarms, especially when the individual IND has leaned only momentarily.

  Moreover, in an advantageous use of tracking, it is possible to store (step 52 of FIG. 4) the new alibi ratio measured at time t1 as a reference ratio replacing the initial ratio r (to), if the test 47 is negative, that is, if the individual IND has put more than the duration St1 to reach the position of the moment t1. This situation may correspond for example to the case where the IND sits slowly and remains substantially in this position, so that if discomfort is then felt by the individual in this sitting position, the tests 46, 47 and 48 can detect a further decrease, but brutal this time, of the alibi report, and the alarm can be triggered at step 51.

  Of course, the present invention is not limited to the embodiment described above by way of example; it extends to other variants.

  Thus, it will be understood that, rather than detecting a variation in the height of a rectangle (or in the ratio of a height to a width of a rectangle), it is possible to provide an additional step of detecting, together with the detection of the decrease in the height of the shape contour, a widening of the shape contour, beyond a second predetermined distance SR2. This variant is more advantageous for monitoring people often sitting, including wheelchair. In this embodiment, if the height al exceeds a first threshold value SR1 and especially if the width b1 exceeds a second threshold value SR2, an alarm can be triggered.

  More generally, the shape chosen for the outline of the individuals, rectangular above, is capable of variants (for example in ellipse, or other).

Claims (10)

claims
  1. A method for detecting falls of persons with limited autonomy, characterized in that it comprises the following steps: a) providing means for taking successive shots of the same plane, b) detecting in said shots a movement to identify a form in motion representative of a person, c) locate a contour of said moving form, and d) detect a decrease in height of said contour shape, beyond a selected threshold difference, said decrease being representative of a fall of said person.
  2. Method according to claim 1, characterized in that said contour shape is a rectangle, and in that it detects a decrease in the height of the rectangle beyond a threshold difference.
  3. Method according to one of claims 1 and 2, characterized in that it comprises a first calibration step to identify only one form of global outline for a person in motion.
  4. Method according to one of the preceding claims, characterized in that said shooting means comprise a wide angle camera.
  5. Method according to one of the preceding claims, characterized in that it comprises the additional steps of: dl) comparing the height of the outline shape to a first date at the height of the same shape contour to a second date, and d2) decree an alert under the following conditions: * if the difference of said heights is greater than the threshold difference, and * if the difference between the first and second dates is less than a first threshold duration, predetermined.
  6. Method according to one of the preceding claims, characterized in that it comprises the following steps consisting of: e) counting a duration from the detection of the fall, and f) trigger an alarm for a duration exceeding one second threshold duration, predetermined.
  7. Method according to one of the preceding claims, characterized in that it further comprises the steps of: cl) perform a follow-up of said moving form, and c2) correct changes in shape contour according to said tracking .
  8. Method according to one of the preceding claims, characterized in that it further comprises a step of detecting, together with the detection of the decrease in the height of the shape contour, an enlargement of the shape contour, beyond beyond a second predetermined distance.
  9. Computer program product, stored in a memory of a processing unit or on a removable medium intended to cooperate with a reader of said processing unit, characterized in that it comprises instructions for the implementation of all or part of the steps of the method according to one of the preceding claims.
  10. Device for detecting falls of persons with limited autonomy, characterized in that it comprises means of shooting connected to a processing unit having a memory adapted to store a computer program product according to claim 9.
FR0405356A 2004-05-17 2004-05-17 Protection for the detection of falls at home, in particular of people with restricted autonomy Active FR2870378B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
FR0405356A FR2870378B1 (en) 2004-05-17 2004-05-17 Protection for the detection of falls at home, in particular of people with restricted autonomy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
FR0405356A FR2870378B1 (en) 2004-05-17 2004-05-17 Protection for the detection of falls at home, in particular of people with restricted autonomy

Publications (2)

Publication Number Publication Date
FR2870378A1 true FR2870378A1 (en) 2005-11-18
FR2870378B1 FR2870378B1 (en) 2008-07-11

Family

ID=34944999

Family Applications (1)

Application Number Title Priority Date Filing Date
FR0405356A Active FR2870378B1 (en) 2004-05-17 2004-05-17 Protection for the detection of falls at home, in particular of people with restricted autonomy

Country Status (1)

Country Link
FR (1) FR2870378B1 (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2398003A1 (en) * 2010-06-21 2011-12-21 General Electric Company Method and system for fall detection
GB2482396A (en) * 2010-07-30 2012-02-01 Gen Electric Detecting a Fallen Person Using a Range Imaging Device
GB2485058A (en) * 2010-10-28 2012-05-02 Gen Electric System and method for monitoring changes in the location of persons and objects
WO2012115878A1 (en) * 2011-02-22 2012-08-30 Flir Systems, Inc. Infrared sensor systems and methods
WO2012115881A1 (en) * 2011-02-22 2012-08-30 Flir Systems, Inc. Infrared sensor systems and methods
FR2985070A1 (en) * 2011-12-21 2013-06-28 Orme System for detecting fall of e.g. person in retirement home, has programmed analysis unit to acquire images taken by sensors in synchronous manner, and to detect fall of person in scene from time sequence of pair of images of scene
EP2763116A1 (en) 2013-02-01 2014-08-06 FamilyEye BVBA Fall detection system and method for detecting a fall of a monitored person
WO2016197385A1 (en) * 2015-06-12 2016-12-15 深圳开源创客坊科技有限公司 Alarm system and method capable of monitoring accidental tumble of human body

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10140832B2 (en) 2016-01-26 2018-11-27 Flir Systems, Inc. Systems and methods for behavioral based alarms

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030004913A1 (en) * 2001-07-02 2003-01-02 Koninklijke Philips Electronics N.V. Vision-based method and apparatus for detecting an event requiring assistance or documentation
US20030058339A1 (en) * 2001-09-27 2003-03-27 Koninklijke Philips Electronics N.V. Method and apparatus for detecting an event based on patterns of behavior

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030004913A1 (en) * 2001-07-02 2003-01-02 Koninklijke Philips Electronics N.V. Vision-based method and apparatus for detecting an event requiring assistance or documentation
US20030058339A1 (en) * 2001-09-27 2003-03-27 Koninklijke Philips Electronics N.V. Method and apparatus for detecting an event based on patterns of behavior

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2398003A1 (en) * 2010-06-21 2011-12-21 General Electric Company Method and system for fall detection
US8508372B2 (en) 2010-06-21 2013-08-13 General Electric Company Method and system for fall detection
GB2482396B (en) * 2010-07-30 2014-11-12 Gen Electric Method and system for detecting a fallen person using a range imaging device
US8427324B2 (en) 2010-07-30 2013-04-23 General Electric Company Method and system for detecting a fallen person using a range imaging device
GB2482396A (en) * 2010-07-30 2012-02-01 Gen Electric Detecting a Fallen Person Using a Range Imaging Device
GB2485058A (en) * 2010-10-28 2012-05-02 Gen Electric System and method for monitoring changes in the location of persons and objects
WO2012115881A1 (en) * 2011-02-22 2012-08-30 Flir Systems, Inc. Infrared sensor systems and methods
WO2012115878A1 (en) * 2011-02-22 2012-08-30 Flir Systems, Inc. Infrared sensor systems and methods
FR2985070A1 (en) * 2011-12-21 2013-06-28 Orme System for detecting fall of e.g. person in retirement home, has programmed analysis unit to acquire images taken by sensors in synchronous manner, and to detect fall of person in scene from time sequence of pair of images of scene
EP2763116A1 (en) 2013-02-01 2014-08-06 FamilyEye BVBA Fall detection system and method for detecting a fall of a monitored person
WO2016197385A1 (en) * 2015-06-12 2016-12-15 深圳开源创客坊科技有限公司 Alarm system and method capable of monitoring accidental tumble of human body

Also Published As

Publication number Publication date
FR2870378B1 (en) 2008-07-11

Similar Documents

Publication Publication Date Title
US10007849B2 (en) Predicting external events from digital video content
Stone et al. Fall detection in homes of older adults using the Microsoft Kinect
US9710761B2 (en) Method and apparatus for detection and prediction of events based on changes in behavior
US10091463B1 (en) Method for determining whether an individual enters a prescribed virtual zone using 3D blob detection
US9892611B1 (en) Method for determining whether an individual enters a prescribed virtual zone using skeletal tracking and 3D blob detection
Auvinet et al. Fall detection with multiple cameras: An occlusion-resistant method based on 3-d silhouette vertical distribution
US20130182905A1 (en) System and method for building automation using video content analysis with depth sensing
US20130054180A1 (en) Method and system for detecting a fall based on comparing data to criteria derived from multiple fall data sets
US6700487B2 (en) Method and apparatus to select the best video frame to transmit to a remote station for CCTV based residential security monitoring
US9277878B2 (en) Image processing sensor systems
US10080513B2 (en) Activity analysis, fall detection and risk assessment systems and methods
EP2741669B1 (en) Bed exit monitoring apparatus
EP1418555B1 (en) Presence detector and use thereof
EP2396776B1 (en) Bed monitoring system
JP4820292B2 (en) Sensor device, system and method associated with an automatic door switch
JP4380252B2 (en) Imaging apparatus and imaging method
EP1461981B1 (en) Method and apparatus for controlling lighting based on user behavior
JP2014236896A (en) Information processor, information processing method, and program
US8175336B2 (en) Target tracker
US7987069B2 (en) Monitoring patient support exiting and initiating response
US20140142460A1 (en) Method for detecting potential falls and a fall detector
US20120245479A1 (en) Physiology Monitoring and Alerting System and Process
JP4881766B2 (en) Inter-camera link relation information generation device
US6774905B2 (en) Image data processing
US8237571B2 (en) Alarm method and system based on voice events, and building method on behavior trajectory thereof

Legal Events

Date Code Title Description
CD Change of name or company name
CJ Change in legal form
PLFP Fee payment

Year of fee payment: 12

PLFP Fee payment

Year of fee payment: 13

PLFP Fee payment

Year of fee payment: 14